Method for extracting face feature by simulating biological vision mechanism

A face feature and biological vision technology, applied in the field of image feature extraction for face recognition, can solve problems such as difficult to achieve real-time processing, large amount of calculation for 3D modeling, and high computational complexity, so as to meet real-time processing requirements and improve recognition The effect of rate and good descriptive ability

Active Publication Date: 2011-02-09
ROPEOK TECHNOLOGY GROUP CO LTD
View PDF4 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem with this type of method is that it is very difficult to model the face in 3D
At present, there are mainly two ways to obtain the 3D model of the face: one is to scan the face in 3D to directly obtain the 3D data of the face, but this method requires special 3D scanning equipment and the cost is too high; Multiple 2D images of the same face with different viewing angles are used to construct a 3D model of the face. The pro

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for extracting face feature by simulating biological vision mechanism
  • Method for extracting face feature by simulating biological vision mechanism
  • Method for extracting face feature by simulating biological vision mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] figure 1 The processing flow of this embodiment is given, which includes the following 6 steps:

[0024] (1) Use the sparse coding model to simulate the learning mechanism of simple cells in the primary visual cortex, and obtain a set of sparse coding basis functions consistent with the statistical characteristics of the image as candidate feature extraction filters. The sparse coding model describes the learning mechanism of simple cells as an optimization problem:

[0025] min : E ( a , φ ) = Σ x , y [ I ( x , y ) - Σ i = 1 N ...

Embodiment 2

[0041] This example is basically the same as the first example, the difference is that the process of enhancing the features through the attention mechanism in step (5) is omitted, so as to improve the speed of feature extraction. In the implementation steps of this example, the feature map C with illumination, expression and translation invariance is obtained in step (4) i (x, y), i=1, 2, L, M, directly put each C i (x, y) are normalized to zero mean and unit variance, and each normalized C i (x, y) are spliced ​​into a column vector by column, and then the M column vectors are spliced ​​into a large column vector as the invariant feature vector of the face image, and the subsequent processing is implemented according to step (6) in Example 1 .

[0042] Computer simulation analysis of the inventive method:

[0043] Use Matlab software on a computer with P4 2.66GHz CPU and 1GB internal memory to carry out simulation analysis on the method of embodiment 1 and 2, the Gabor wa...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for extracting a face feature by simulating a biological vision mechanism, and belongs to the field of image processing and pattern recognition. The method comprises the following steps of: simulating a learning mechanism of primary visual cortex simple cells, training a group of filters for describing a simple cell receptive field, and selecting a small number ofillumination invariant features of image extracted by the filter, which have the specific frequency selectivity, from the group of filters; simulating the function of primary visual cortex complex cells, and adding the expression and the translational invariance of the feature on the basis of the illumination invariance; strengthening a salient region of the invariant feature by using a visual attention mechanism; and converting the strengthened invariant feature into a characteristic vector for face recognition. An experiment shows that the method can effectively reduce the influence of illumination, expression and translation change on face recognition effect, and has real-time processing capability.

Description

technical field [0001] The invention belongs to the fields of image processing and pattern recognition, in particular to an image feature extraction method for face recognition that simulates a biological vision mechanism. Background technique [0002] Since automatic face recognition has broad application prospects in the fields of commerce, military and security, face recognition technology has received extensive attention in recent years and has achieved considerable development. At present, face recognition has achieved good results under controlled conditions. However, in practical applications, external factors such as illumination and expression seriously affect the performance of face recognition, and when these factors change, the effect of face recognition will drop sharply. In order to effectively describe faces under different changing conditions and ensure the effect of face recognition, there are currently two main methods: one is to collect a large number of ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/46G06K9/66
Inventor 龚卫国杜兴李伟红张睿白志黄庆忠罗凌熊健
Owner ROPEOK TECHNOLOGY GROUP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap